FDQN: A Flexible Deep Q-Network Framework for Game Automation

TL;DR

The paper introduces FDQN, a flexible deep Q-network framework that adapts to various game environments, processing high-dimensional data in real-time and outperforming existing models in multiple game benchmarks.

Contribution

It presents a novel adaptive DQN framework capable of handling diverse gaming environments with real-time processing and dynamic architecture adjustment.

Findings

Outperforms baseline models in Atari and Chrome Dino games

Successfully adapts to different HTML-based game environments

Demonstrates potential for real-world application and future exploration

Abstract

In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This work proposes a state-of-the-art Flexible Deep Q-Network (FDQN) framework that can address this challenge with a selfadaptive approach that is processing high-dimensional sensory data in realtime using a CNN and dynamically adapting the model architecture to varying action spaces of different gaming environments and outperforming previous baseline models in various Atari games and the Chrome Dino game as baselines. Using the epsilon-greedy policy, it effectively balances the new learning and exploitation for improved performance, and it has been designed with a modular structure that it can be easily adapted to other HTML-based games without touching the core part of the framework. It is demonstrated that the FDQN framework can successfully solve a well-defined task in a laboratory condition, but more importantly it also discusses potential applications to more challenging real-world cases and serve as the starting point for future further exploration into automated game play and beyond.